Image de couverture de livre

AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Jingbo, Chong, Wenyue, Tu, Songjun, Zhang, Qichao, Zhang, Yaocheng, Chai, Jiajun, Wang, Xiaohan, Lin, Wei, Yin, Guojun, Zhao, Dongbin
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
par: Zhang, Yaocheng, et autres
Publié: (2026)

Are Full Rollouts Necessary for On-Policy Distillation?
par: Zhang, Yaocheng, et autres
Publié: (2026)

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
par: Tu, Songjun, et autres
Publié: (2024)

Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning
par: Sun, Jingbo, et autres
Publié: (2025)

Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model
par: Tu, Songjun, et autres
Publié: (2024)

Dynamic Dual-Granularity Skill Bank for Agentic RL
par: Tu, Songjun, et autres
Publié: (2026)

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
par: Fu, Yuqian, et autres
Publié: (2025)

RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
par: Fu, Yuqian, et autres
Publié: (2025)

CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
par: Zhang, Yaocheng, et autres
Publié: (2025)

Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
par: Sun, Jingbo, et autres
Publié: (2026)

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
par: Tu, Songjun, et autres
Publié: (2025)

LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services
par: He, Hang, et autres
Publié: (2025)

AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
par: Mei, Lang, et autres
Publié: (2025)

Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization
par: Tu, Songjun, et autres
Publié: (2025)

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
par: Shen, Jianghan, et autres
Publié: (2026)

Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
par: Wang, Zili, et autres
Publié: (2026)

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay
par: Hu, Zhexin, et autres
Publié: (2026)

ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIs
par: Chen, Hao, et autres
Publié: (2025)

PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review
par: Tu, Songjun, et autres
Publié: (2026)

AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards
par: Lin, Zihan, et autres
Publié: (2025)

SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
par: Zhang, Qi, et autres
Publié: (2026)

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
par: Wang, Li, et autres
Publié: (2026)

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
par: Lin, Zihan, et autres
Publié: (2026)

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
par: Lin, Zihan, et autres
Publié: (2025)

MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
par: Xu, Zekun, et autres
Publié: (2025)

Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
par: Wang, Li, et autres
Publié: (2026)

Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
par: Fu, Yonggan, et autres
Publié: (2020)

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
par: Lu, Xiaodong, et autres
Publié: (2026)

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation
par: Tu, Songjun, et autres
Publié: (2025)

Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
par: Xia, Tianle, et autres
Publié: (2026)

Gen-Searcher: Reinforcing Agentic Search for Image Generation
par: Feng, Kaituo, et autres
Publié: (2026)

RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
par: Zeng, Wenwen, et autres
Publié: (2026)

REVERSE: Reinforcing Evidence Verification and Search for Agentic Image geo-localization
par: Li, Yong, et autres
Publié: (2026)

Promoting Efficient Reasoning with Verifiable Stepwise Reward
par: Yue, Chuhuai, et autres
Publié: (2025)

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
par: Wei, Zhenlin, et autres
Publié: (2026)

Agentic Reinforcement Learning for Search is Unsafe
par: Yang, Yushi, et autres
Publié: (2025)

DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking
par: Lan, Tian, et autres
Publié: (2025)

Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems
par: Fan, Dongzhe, et autres
Publié: (2026)

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
par: Fu, Yonggan, et autres
Publié: (2021)

A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat
par: Chai, Jiajun, et autres
Publié: (2022)